Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare read-only/idempotent/open-world safety; the description goes well beyond that by disclosing the internal pipeline (detect shapes, read text, match catalog), the ordering of results, the exact result fields, the presence of a licensing note, and a scope exclusion ("Assets marked AI-generated are excluded"). The quality caveats tell the agent how to predict failure, which annotations cannot convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose, then inputs, then return contents, then fit caveats — a sensible order. It is a single dense paragraph of long compound sentences, which is heavier than needed, but essentially every clause carries information an agent would use.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, and the description compensates by enumerating the returned fields, their ordering, and the licensing note. Combined with the quality caveats and the OCR fallback, an agent has everything needed to call it and interpret the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description mentions the `text` argument and its one-character-per-shape rule, but the schema already states both that rule and that it is for unreadable images, so the description adds little new parameter meaning; size clamping and the image_url/image_data alternative are likewise schema-only.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Identify the font in an image of text") plus the output artifact ("closest matching Creative Market font products"). None of the siblings (search_products, browse_category, find_similar, etc.) do image-based font identification, so the tool's niche is unambiguous from the first clause.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete conditions of good fit ("a crop of a few clear, separated letters on a plain background") and poor fit ("connected script letters, low-resolution images and busy backgrounds"), plus the fallback path when OCR fails via the `text` argument. It does not route the agent to any sibling tool for related follow-ups, which is the only gap.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.